{
  "best_metric": 1.4412074089050293,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.7920792079207921,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.031683168316831684,
      "grad_norm": 123.59939575195312,
      "learning_rate": 5e-05,
      "loss": 4.0351,
      "step": 1
    },
    {
      "epoch": 0.031683168316831684,
      "eval_loss": 4.633000373840332,
      "eval_runtime": 19.8883,
      "eval_samples_per_second": 21.42,
      "eval_steps_per_second": 1.358,
      "step": 1
    },
    {
      "epoch": 0.06336633663366337,
      "grad_norm": 140.6913299560547,
      "learning_rate": 0.0001,
      "loss": 4.3784,
      "step": 2
    },
    {
      "epoch": 0.09504950495049505,
      "grad_norm": 132.14886474609375,
      "learning_rate": 9.989294616193017e-05,
      "loss": 4.063,
      "step": 3
    },
    {
      "epoch": 0.12673267326732673,
      "grad_norm": 72.3555908203125,
      "learning_rate": 9.957224306869053e-05,
      "loss": 2.9489,
      "step": 4
    },
    {
      "epoch": 0.15841584158415842,
      "grad_norm": 53.992122650146484,
      "learning_rate": 9.903926402016153e-05,
      "loss": 2.3328,
      "step": 5
    },
    {
      "epoch": 0.1900990099009901,
      "grad_norm": 39.890628814697266,
      "learning_rate": 9.829629131445342e-05,
      "loss": 2.0503,
      "step": 6
    },
    {
      "epoch": 0.22178217821782178,
      "grad_norm": 20.836332321166992,
      "learning_rate": 9.73465064747553e-05,
      "loss": 1.7499,
      "step": 7
    },
    {
      "epoch": 0.25346534653465347,
      "grad_norm": 10.976515769958496,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.7231,
      "step": 8
    },
    {
      "epoch": 0.2851485148514851,
      "grad_norm": 19.44645118713379,
      "learning_rate": 9.484363707663442e-05,
      "loss": 1.7058,
      "step": 9
    },
    {
      "epoch": 0.31683168316831684,
      "grad_norm": 10.474262237548828,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.5838,
      "step": 10
    },
    {
      "epoch": 0.3485148514851485,
      "grad_norm": 6.232975006103516,
      "learning_rate": 9.157348061512727e-05,
      "loss": 1.3863,
      "step": 11
    },
    {
      "epoch": 0.3801980198019802,
      "grad_norm": 6.1638288497924805,
      "learning_rate": 8.966766701456177e-05,
      "loss": 1.3966,
      "step": 12
    },
    {
      "epoch": 0.41188118811881186,
      "grad_norm": 6.118275165557861,
      "learning_rate": 8.759199037394887e-05,
      "loss": 1.3583,
      "step": 13
    },
    {
      "epoch": 0.44356435643564357,
      "grad_norm": 7.997486591339111,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.398,
      "step": 14
    },
    {
      "epoch": 0.4752475247524752,
      "grad_norm": 9.315695762634277,
      "learning_rate": 8.296729075500344e-05,
      "loss": 1.4856,
      "step": 15
    },
    {
      "epoch": 0.5069306930693069,
      "grad_norm": 13.862922668457031,
      "learning_rate": 8.043807145043604e-05,
      "loss": 1.6599,
      "step": 16
    },
    {
      "epoch": 0.5386138613861386,
      "grad_norm": 15.675683975219727,
      "learning_rate": 7.777851165098012e-05,
      "loss": 1.6805,
      "step": 17
    },
    {
      "epoch": 0.5702970297029702,
      "grad_norm": 8.870408058166504,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.3952,
      "step": 18
    },
    {
      "epoch": 0.601980198019802,
      "grad_norm": 6.7011189460754395,
      "learning_rate": 7.211443451095007e-05,
      "loss": 1.3927,
      "step": 19
    },
    {
      "epoch": 0.6336633663366337,
      "grad_norm": 5.8261213302612305,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.3644,
      "step": 20
    },
    {
      "epoch": 0.6653465346534654,
      "grad_norm": 4.526528835296631,
      "learning_rate": 6.607197326515808e-05,
      "loss": 1.3722,
      "step": 21
    },
    {
      "epoch": 0.697029702970297,
      "grad_norm": 6.313098907470703,
      "learning_rate": 6.294095225512603e-05,
      "loss": 1.406,
      "step": 22
    },
    {
      "epoch": 0.7287128712871287,
      "grad_norm": 9.860219955444336,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 1.5312,
      "step": 23
    },
    {
      "epoch": 0.7603960396039604,
      "grad_norm": 9.333724975585938,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 1.5527,
      "step": 24
    },
    {
      "epoch": 0.7920792079207921,
      "grad_norm": 6.874697685241699,
      "learning_rate": 5.327015646150716e-05,
      "loss": 1.5393,
      "step": 25
    },
    {
      "epoch": 0.7920792079207921,
      "eval_loss": 1.4412074089050293,
      "eval_runtime": 19.9527,
      "eval_samples_per_second": 21.35,
      "eval_steps_per_second": 1.353,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.0952750720352256e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}